The authors designed a system in which five complementary roles translate a high-level concept into structured rules, executable dynamics, and visual observations.
Executable code gives generative worlds persistent rules and evolving state
CoDeR separates world simulation from visual rendering, coordinating five roles to build executable dynamics and turn their evolving state into video.
Chinese Tech
Zixun Fang · Yawen Shao · Kai Zhu · Jie Xiao · Shihan Chen · Yu Liu · +4 more
USTC · TongYi Lab
Research Digest··2 min read
Fang and colleagues present CoDeR, a world-modeling framework that represents rules, entities, and state explicitly in code rather than only through generated video.
Why this paper
From TongYi Lab and USTC · Part of World Model Planning for Agents, now 19 papers
In one line
CoDeR enables world models with long-term memory, open-ended interactions, autonomous evolution, and multi-agent dynamics.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§